Re: [PATCH] percpu: Allow to kill tasks doing pcpu_alloc() and waiting for pcpu_balance_workfn()

[Andrew Morton <akpm@linux-foundation.org>]

On Wed, 14 Mar 2018 14:51:48 +0300 Kirill Tkhai <ktkhai@virtuozzo.com> wrote:

> In case of memory deficit and low percpu memory pages,
> pcpu_balance_workfn() takes pcpu_alloc_mutex for a long
> time (as it makes memory allocations itself and waits
> for memory reclaim). If tasks doing pcpu_alloc() are
> choosen by OOM killer, they can't exit, because they
> are waiting for the mutex.
> 
> The patch makes pcpu_alloc() to care about killing signal
> and use mutex_lock_killable(), when it's allowed by GFP
> flags. This guarantees, a task does not miss SIGKILL
> from OOM killer.
> 
> ...
>
> --- a/mm/percpu.c
> +++ b/mm/percpu.c
> @@ -1369,8 +1369,12 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
>  		return NULL;
>  	}
>  
> -	if (!is_atomic)
> -		mutex_lock(&pcpu_alloc_mutex);
> +	if (!is_atomic) {
> +		if (gfp & __GFP_NOFAIL)
> +			mutex_lock(&pcpu_alloc_mutex);
> +		else if (mutex_lock_killable(&pcpu_alloc_mutex))
> +			return NULL;
> +	}

It would benefit from a comment explaining why we're doing this (it's
for the oom-killer).

My memory is weak and our documentation is awful.  What does
mutex_lock_killable() actually do and how does it differ from
mutex_lock_interruptible()?  Userspace tasks can run pcpu_alloc() and I
wonder if there's any way in which a userspace-delivered signal can
disrupt another userspace task's memory allocation attempt?